Neural Networks Based Predictive Control for TRT

摘要

This paper presents a neural network based predictive control for TRT (Top Gas Pressure Recovery Turbine). TRT is a nonlinear system with time-delay. To keep the top gas pressure stable, predictive control is developed and a RBF neural network which is trained using the input-output data of the practical process as predictive model. RBFNN (radial basis function neural network) can approach any nonlinear function in theory. Simulation results show that the neural network based predictive controller can obtain satisfactory performance in top gas pressure control.